JPH07121313A - Disk device - Google Patents

Abstract

PURPOSE:To prevent a system bus from being occupied for a long time by shortening the retry time as much as possible at the time of performing the retry processing because of the occurrence of error. CONSTITUTION:The device which executes read of plural data blocks by one command is provided with a retry control part 28 and a transfer mode switching means (AND circuit 29); and if a read error occurs, a retry request is reported to a host by a retry control part, and the transfer mode is switched, and data of the command is transferred again in the buffer mode. Pointer save means (30 and 31) are provided, and if a read error occurs, a retry request is reported to the host by the retry control part, and the buffer pointer of an already read data block is saved by the pointer save means, and read is started from an unread data block at the time of executing recommand.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a disk device (optical disk device, magnetic disk device, etc.) for reading a plurality of data blocks on a medium with one command.

[0002]

2. Description of the Related Art FIGS. 10 and 11 are views showing a conventional example. In FIGS. 10 and 11, 1 is a host (host device), 2
Is an optical disk device, 3 is an I / O device (I / O-1, I / O
O-2, I / O-3 ...), 5 is a disk controller,
6 is a command control unit, 7 is a retry processing unit, 8 is a data buffer, 9 is a multiplexer (MPX), 10 is a comparator, 11 is a read-in pointer (hereinafter referred to as “RI pointer”), and 12 is a read-out pointer ( Less than,
"RO pointer").

Further, d1, d2, d3, d4, d5 ...
Indicates a data block, T ₀ indicates time (system bus occupation time), and RD indicates a read command. The conventional optical disk device will be described below.

§1: Description of optical disk device ... FIG. 10
Reference FIG. 10 is an explanatory diagram 1 of the prior art. Conventionally, in an optical disk device that reads a plurality of data blocks on a medium with one command, a device equipped with a data buffer in a disk control device is known in order to absorb the difference between the transfer speed on the host side and the reading speed of the optical disk device. It was being done.

A disk control device of such an optical disk device is constructed as shown in FIG. 10, for example. As shown, the disk controller 5 includes a command controller 6,
Retry processing unit 7, data buffer 8, multiplexer 9, comparator 10, RI pointer 11, RO pointer 12
Etc. are provided and the following operations are performed.

First, in response to a command from the host, the command control section 6 outputs a control signal to drive the drive device. By driving the drive device, for example, when the command is a read command, data is read from the medium.

The data read from the medium is transferred from the drive device to the disk controller 5 and temporarily stored in the data buffer 8. Then data buffer 8
To the host.

In the process of this data transfer, the following processing is performed. That is, the RI pointer 11 counts the data blocks read from the medium, and the RO pointer 12 counts the data blocks transferred from the data buffer 8 to the host.

Then, the RI pointer 11 and the RO pointer 12 are compared by the comparator 10, and the block data existing in the data buffer 8 is multiplexed (MP).
X) 9 is selected to perform the data transfer.

When a read error occurs during the above operation, the drive device reports an error signal to the disk controller 5. This error signal is received by the retry processing unit 7, and the retry processing unit 7 notifies the command control unit 6 of the retry method “a”. Then, the data block in which the error has occurred is retried, and the data is read again.

§2: Description of system configuration and retry process ... See FIG. 11. FIG. 11 is an explanatory diagram 2 of the prior art, FIG. 11A is a system configuration diagram, and FIG. 11B is a time chart.

The optical disk device operates as a system configuration as shown in FIG. 11A, for example. In this example, a host 1, an optical disk device (device having the configuration shown in FIG. 10) 2, and another I / O device (I
/ O-1, I / O-2, I / O-3 ...) 3 are connected.

In the above optical disk device, in order to shorten the command processing time for data transfer, the FIFO mode in which the transfer is started from the block where the reading is completed is adopted. However, when a read error occurs in the block in the middle, the host 1 The data transfer will be interrupted and the retry will be executed with the connection of.

Further, if a single I / O device occupies the system bus for a long time, other I / O devices cannot operate and the performance is degraded, and the connection time exceeds a specified value. Then, the host 1 judges that there is an error.

For example, in the example of FIG. 11B, it becomes as follows. First, if the host 1 issues a read command RD, the optical disk device 2 performs a seek, and a plurality of data blocks d1, d2, d3, d4 ... From the medium.
Read.

The read data block is transferred to the system bus via the data buffer 8 and then fetched by the host 1. It is assumed that an error (see X in the figure) occurs during the reading of the data block d4 during execution of such a read command. At this time, the optical disk device 2 retries the data block d4 (rotation waiting retry) while occupying the system bus, and if the retry is successful, the data transfer from the data block d4 is performed subsequent to the above process.

In this example, the optical disk device 2 occupies the system bus during the time T ₀ shown in the figure, and the other I / O device 3 is used.
Will not work. Further, if the connection time to the system bus exceeds the specified value, the host 1 will determine that there is an error.

Therefore, in order to shorten the connection time with the host 1, SCSI (Small Computer Standard Interf
ace) defines the following functions. : "Store pointer message" from the I / O device side
This saves the data pointer on the host side and disconnects the interface.

In response to a "restore pointer message" from the I / O device side, the host side data pointer is reset and data transfer is restarted. However, most of the current S
The CSI host does not support the above functions, and the mainframe BMC (Block Multip
lexer Channel) does not have this function. Therefore, in the I / O device, it is required to shorten the retry time as much as possible, and it is a particularly strict requirement in the optical disc device which requires a great amount of retry time.

[0020]

SUMMARY OF THE INVENTION The above-mentioned conventional device has the following problems. (1): In a disk device that reads a plurality of data blocks with one command, when a read error occurs in an intermediate block as described above, the data transfer is interrupted and a retry is performed.

In this case, since a single I / O device occupies the system bus for a long time, other I / O devices cannot operate. Therefore, not only the performance is degraded, but also the host determines that an error occurs when the connection time exceeds the specified value.

(2): Most of the current SCSI hosts do not support the above functions, and the BMC (block multiplexer channel) of the mainframe does not have this function.

Therefore, in the I / O device, it is required to shorten the retry time as much as possible, and in the optical disk device which requires a great amount of retry time, there is a particularly severe requirement.

An object of the present invention is to solve such a conventional problem and to shorten the retry time as much as possible and prevent the system bus from being occupied for a long time when a read error occurs and a retry is performed. .

[0025]

FIG. 1 is a diagram for explaining the principle of the present invention. In FIG. 1, the same parts as those in FIGS. 10 and 11 are designated by the same reference numerals. Further, 14 is a drive device, 28 is a retry control unit, 29 is an AND circuit, 30 is a pointer control unit, 31 is a register, 32 is a retry timer unit, and 33 is a retry determination unit.

In order to solve the above problems, the present invention has the following configuration. When a data read from a medium is transferred to the host 1, a data buffer 8 for temporarily storing the transfer data and a retry processing unit 7 for performing a retry process when a read error occurs are provided, and a command for reading a plurality of data blocks is provided. In the disk device to be executed in step 1, when a read error occurs, the retry control unit 28 that reports a retry request to the host 1 and the control of the retry control unit 28
A transfer mode switching unit (AND circuit 29) for switching the transfer mode of the data buffer 8 is provided, and when a read error occurs, the retry control unit 28 reports a retry request to the host 1 and the transfer mode switching unit transfers the transfer mode. A disk device that transfers data for re-commands in buffer mode by switching.

In the configuration, a pointer save means (pointer control unit 30, register 31) for saving the buffer pointer of the read data block is provided,
When a read error occurs, the retry control unit 28 reports a retry request to the host 1, and the pointer save means saves the buffer pointer of the read data block. The disk device that starts reading.

In the configuration or in the configuration, a retry timer unit 32 for monitoring the retry time is provided, and when a read error occurs, the retry timer unit 32 monitors the retry time. A disk device that performs a retry and, if it exceeds the limit, activates the retry control unit 28 and reports a retry request to the host 1.

In the configuration, a retry determination unit 33 for determining the length of the retry time and switching the retry is provided, and when a read error occurs, the retry determination unit 33 determines the length of the retry time, and the result In the case of a retry that requires a long time, the retry control unit 28 is activated to report a retry request to the host, and in the case of a short time retry, the retry timer unit 32 is activated to monitor the retry time. As a result, the disk device that performs each of the retries switched according to the determination result of the retry determination unit 33.

[0030]

The operation of the present invention based on the above configuration will be described with reference to FIG. (1): In the configuration described above, when a read error occurs, the retry control unit 28 reports a retry request to the host 1 based on the information from the retry processing unit 7, and performs retry by command reissue.

In this retry, all the designated data blocks are read from the host 1, stored in the data buffer 8, and then combined with the host 1 to transfer the data in the data buffer 8 (buffer mode). In this way, the coupling time with the host 1 is shortened.

(2): In the above configuration, when a read error occurs, the retry control unit 28 reports a retry request to the host 1 and the pointer control unit 30 constituting the pointer save means controls the read data. The buffer pointer of the block is saved in the register 31.

At this time, the data that has already been read is left in the data buffer 8, and when the command is reissued,
Read from the data block that was the target of the retry. After reading all the data blocks, the retry time is shortened by transferring the data from the first data in the data buffer 8.

(3): The configuration is as follows. That is, in the above retry processing, the command reissue of the host 1 is required, and the overhead of the host 1 increases. In order to reduce this, in the configuration, the retry timer unit 32
To monitor the retry time. Then, a retry within the connection monitoring time of the host 1 is processed in the disk controller 5, and only when a retry exceeding this is necessary, a retry request is reported to the host and the retry is performed. In this way the frequency of command reissues is reduced.

(4): The configuration is as follows. That is, in the retry process of (3), the system bus is occupied within the retry monitoring time, so that an I / O error does not occur, but the overhead of the system bus increases and system performance is affected.

Therefore, in this case, the retry determination unit 33
The retry time is determined according to the above, and if a retry requires a long time, the process of (1) or (2) above is executed.If the retry is a short time, the process of (3) above is executed. By doing so, the retry time can be shortened.

(5): As described above, when a read error occurs and retry processing is performed, the retry time can be shortened as much as possible and the system bus can be prevented from being occupied for a long time.

[0038]

Embodiments of the present invention will be described below with reference to the drawings. 2 to 9 are views showing an embodiment of the present invention,
2 to 9, the same components as those in FIGS. 1, 10 and 11 are designated by the same reference numerals.

Further, 16 is a control unit, 17 is a read circuit,
Reference numeral 18 is a write circuit, 19 is a servo control unit, 20 is a head (optical head), 21 is a light amount control unit, 22 is a spindle control unit, 23 is a spindle motor, 24 is an optical disk (medium), and 25 is a magnetic field generation unit. .

(Description of Embodiment 1) FIGS. 2 to 4 are views showing Embodiment 1 of the present invention. The first embodiment will be described below with reference to FIGS.

§1: Description of the configuration of the optical disk device ...
2 and FIG. 3. FIG. 2 is a block diagram of the optical disc device of the first embodiment, and FIG. 3 is a block diagram of the disc control device of the first embodiment. Hereinafter, the configuration of the optical disc device according to the first embodiment will be described with reference to FIGS.

As shown in FIG. 2, the optical disk device 2
Consists of the disk controller 5 and the drive unit 14,
The drive unit 14 includes a control unit 16 and a read circuit 1.
7, write circuit 18, servo control unit 19, head (optical head) 20, light amount control unit 21, spindle control unit 2
2, spindle motor 23, optical disk (medium) 24,
A magnetic field generator 25 and the like are provided.

The optical disk device 2 is connected to the host (host device) 1. Further, the disk controller 5 includes a command controller 6, a retry processor 7, a data buffer 8, a multiplexer 9, a comparator 10, and a RI.
Pointer 11, RO pointer 12, retry controller 2
8, AND circuit 29, etc. are provided. Functions and the like of the above-mentioned respective parts are as follows.

(1): The disk control device 5 is a device (host controller) that performs command exchange, data transfer control, etc. (interface control) with the host 1 and various controls within the optical disk device 2. is there.

(2): The controller 16 controls the disk controller 5
Commands, data transfer control, and control of the servo control unit 19, the light amount control unit 21, the spindle control unit 22, and the like.

(3): The servo control section 19 drives and controls the head 20 (seek control, etc.) according to an instruction from the control section 16. (4): The light quantity control unit 21 controls the laser diode which is the light source in the head 20, and the optical disk (medium) 24
The light amount of the laser beam applied to the interior is adjusted.

(5): The spindle control section 22 controls the rotation of the spindle motor 23. (6): The spindle motor 23 rotationally drives the optical disk 24 via the spindle mechanism.

(7): The head (optical head) 20 irradiates the optical disk 24 with laser light to read / write data. (8): The read circuit 17 is a circuit that processes a read signal when reading data from the optical disc 24.

(9): The write circuit 18 is the optical disc 24
It is a circuit that processes write data when writing data to the memory. (10): The magnetic field generation unit 25 generates a magnetic field on the optical disc 24 when writing data on the optical disc 24.

(11): The retry controller 28 performs various retry controls (retry request to the host, transfer suppression control of data transfer, etc.) based on the information from the retry processor 7 when an error occurs. is there.

(12): AND circuit (AND gate) 29
Is a circuit for closing the gate by the transfer inhibition signal “c” output from the retry control unit 28 to inhibit data transfer.

Since the other construction is the same as that of the conventional example, the description thereof will be omitted. §2: Outline of operation of optical disk device ... FIGS. 2 and 3
When the optical disc 24 is inserted into the optical disc device 2, the control unit 16 detects the medium insertion state based on information from a sensor (not shown) that detects that the medium has been inserted. Recognize media insertion.

Read / write on the optical disk 24 (medium)
When performing writing, the control unit 16 causes the servo control unit 19 and the light amount control unit 2 to operate according to an instruction from the disk control device 5.
1. A control signal is sent to the spindle control unit 22 and the like to start control.

With this control, the spindle control section 22 rotates the spindle motor 23 to control the rotation, and the light quantity control section 21 turns on the laser diode in the head 20 and controls the intensity of the laser beam as instructed. To do. The servo control unit 19 also controls the drive of the head 20 (positioning control, etc.).

In this case, when the data is reproduced, the read signal read via the head 20 is applied to the read circuit 17.
And demodulates and sends it to the disk controller 5. After that, the data is transferred from the disk controller 5 to the host 1.

On the other hand, at the time of writing data, the disk controller 5 sends the data received from the host 1 to the write circuit 18, and the data processed by the write circuit 18 is sent to the head 20 to write it on the medium. In this case, under the control of the control unit 16, the magnetic field generation unit 25 is driven to generate a magnetic field from the outside of the medium.

At the time of reproducing the above-mentioned data, the disk controller 5 operates as follows. First, in response to a command from the host 1, the command control unit 6 outputs a control signal to the control unit 16 of the drive device 14 to drive the drive device 14.

When the command is a read command, the data read from the medium in the drive unit 14 is transferred from the read circuit 17 of the drive unit 14 to the disk controller 5. The transferred data is once stored in the data buffer 8 and then transferred from the data buffer 8 to the host 1. In this data transfer process, the following processing is performed.

That is, the data blocks read from the medium are counted by the RI pointer 11, and the data blocks transferred from the data buffer 8 to the host 1 are counted by the RO pointer 12.

In this case, in the normal time (normal time), the transfer inhibition signal “c” output from the retry control unit 28 is off (high level “1” state), and the RI pointer 11
Then, the pointer of the RO pointer 12 is compared by the comparator 10, and the data existing in the data buffer 8 is selected by the multiplexer (MPX) 9 to perform the data transfer.

When an error occurs during the reading process as described above, the drive device 14 reports an error signal to the disk controller 5. This error signal is received by the retry processing unit 7, and the retry processing unit 7 notifies the command control unit 6 of the retry method “a”.

Further, the retry controller 28 reports a retry request "b" to the host 1 (error report for the retry request) based on the information from the retry processor 7. Then, the data block on the medium in which the error has occurred is retried, and the data is read from the medium again. Hereinafter, the retry process will be described in detail.

§3: Description of Processing of First Embodiment--See FIG. 4 FIG. 4 is a time chart of the first embodiment. Hereinafter, the retry process of the first embodiment will be described with reference to FIG.

In the first embodiment, when an error occurs in the read data block, an error report for a retry request is sent to the host 1 and a retry is executed by reissuing the command.

In this retry, after reading all the designated data blocks from the host 1 and storing them in the data buffer 8, the data is stored in the data buffer 8 and then combined with the host 1 to transfer the data in the data buffer 8 (buffer mode). Reduce the binding time of.

As shown in the figure, it is assumed that a read command RD-1 (first read command) is issued from the host 1 and this command instructs the optical disk device to read the data blocks 1 to 3 on the medium. .

At this time, under the control of the disk controller 5, the drive device 14 seeks and reads the data blocks 1 to 3 on the medium. Then, the data read from the medium is transferred from the read circuit 17 to the data buffer 8 of the disk controller 5 and stored in the data buffer 8. After that, the data stored in the data buffer 8 is sequentially read (FIFO mode) and transferred to the host 1.

In this case, for example, it is assumed that an error (see the portion X in the drawing) occurs when reading the data block 3. When an error occurs in this way, the retry processing unit 7 receives the error signal from the control unit 16, and thereafter,
The retry control unit 28 reports the retry request “b” to the host 1 (error report). With this retry report, the read command is restarted (read command R
D-2 is issued). After the read command RD-2 is issued, the system bus connected to the host is released.

Further, at this time, the retry control unit 28 causes the AN
The transfer inhibition signal “c” output to the D circuit 29 is turned on (low level “0”), and the data buffer 8
The transfer of the.

In the restarted read command RD-2, the transfer control signal “c” is turned on (low level “low” by the retry controller 28 until the data of all the data blocks 1 to 3 are read. 0 ”), the transfer of the data buffer 8 is suppressed, and the read data is buffered in the data buffer 8 in this state.

That is, as described above, when the transfer inhibition signal "c" is turned on (low level "0"), the AND circuit 29 turns off the gate, and the RI pointer 1 is turned on.
The pointer value of 1 is not output to the comparator 10. Therefore, the pointer value of the RI pointer 11 and the RO pointer 12
The pointer values become equal and the data transfer from the data buffer 8 to the host 1 is stopped.

In this state, the read data is buffered as described above. Then data block 1
After reading 3 to 3, the retry control unit 28 turns off the transfer inhibition signal “c” (high level “1”).
As a result, the AND circuit 29 is in the gate-on state,
The pointer value of the RI pointer 11 is input to the comparator 10,
The multiplexer 9 is switched to restart the data transfer from the data buffer 8 to the host 1.

In this processing, as described above, T ₁ (T ₁ : system bus release from when the host 1 issues the read command RD-2 to when data transfer from the data buffer 8 to the host 1 is restarted). System bus is open during the time).

(Explanation of Second Embodiment) FIGS. 5 and 6 are views showing a second embodiment of the present invention. Second Embodiment A second embodiment will be described with reference to FIGS.

§1: Description of configuration of optical disk device ...
See FIG. 5. FIG. 5 is a block diagram of the disk control device of the second embodiment.
The configuration of the optical disc device according to the second embodiment will be described below with reference to FIG. In the second embodiment, the block diagram of the optical disk device shown in FIG. 2 is the same.

As shown, the disk controller 5 has
Command control unit 6, retry processing unit 7, data buffer 8, multiplexer 9, comparator 10, RI pointer 1
1, a RO pointer 12, a retry controller 28, an AND circuit 29, a pointer controller 30, a register 31, etc. are provided.

The pointer control unit 30 has a register 31.
By outputting a save signal “d” to
The control is performed to fetch the pointer value of the I pointer 11 into the register 31 or reset the pointer value set in the register 31 to the RI pointer 11.

The register 31 has the RI pointer 11
Is a register for temporarily setting the pointer value of. In addition,
The other structure is the same as that of the first embodiment, and the description thereof is omitted. §2: Description of processing of the second embodiment--see FIG. 6 FIG. 6 is a time chart of the second embodiment. Hereinafter, the process of the second embodiment will be described with reference to FIG.

In the second embodiment, the data that has already been read is left in the data buffer 8 at the time of retry, and when the command is reissued, the data block to be retried is read. Then, after the reading of all the data blocks is completed, the retry time is shortened by transferring the data from the first data in the data buffer 8 to the host.

As shown in the figure, it is assumed that the host 1 issues a read command RD-1 (first read command), and this command instructs the optical disk device to read the data blocks 1 to 3 on the medium. .

At this time, in response to a control signal from the disk controller 5, the drive unit 14 seeks and reads the data blocks 1 to 3 on the medium. Then, the data read from the medium is transferred from the read circuit 17 to the data buffer 8 of the disk controller 5 and stored in the data buffer 8.

After that, the data stored in the data buffer 8 is sequentially read and transferred to the host 1 (FIFO).
mode). In this case, for example, it is assumed that an error (see the portion X in the figure) has occurred in the data block 3. When an error occurs in this way, the error signal from the control unit 16 is
The retry processing unit 7 receives it, and then the retry control unit 28 reports the retry request “b” to the host 1. Based on this retry report, the restart of the read command (read command RD-2) is received.

When an error occurs, data transfer is suppressed by the transfer suppression signal "c" output from the retry control unit 28 in the same manner as in the first embodiment, and the data for which buffering has been completed is It is left in the data buffer 8. After that, when the read command RD-2 (second read command) is issued, the system bus is released.

When an error occurs in reading the data block 3 as described above, the pointer control unit 30 turns on the save signal “d” output to the register 31 (for example, high level “1”). Then, the pointer value of the RI pointer 11 that has been read into the data buffer 8 is saved in the register 31.

That is, since the error has occurred in the data block 3, the pointer value of the RI pointer 11 is 2. Therefore, when the value of the RI pointer 11 is saved in the register 31 by the save signal "d", the value of the register becomes 2.

Thereafter, the host 1 sends the read command RD-
When 2 (second read command) is issued, the value of the register 31 is reset to the RI pointer 11 under the control of the pointer control unit 30, and the drive device 14 reads only the data block 3 from the medium and the data buffer 8
Transfer to.

Thereafter, the data of the data blocks 1 and 2 stored in the data buffer 8 and the data of the data block 3 reread this time are transferred to the host 1. In this case, the transfer inhibition signal “c” output from the retry control unit 28 is turned off (high level “1”) so that the pointer value of the RI pointer 11 can be output to the comparator 10 (this point is implemented. Same as Example 1).

In this processing, T ₂ (T ₂ : system bus release from when the host 1 issues the read command RD-2 to when data transfer from the data buffer 8 to the host 1 is restarted as described above. System bus is open during the time).

(Description of Third Embodiment) FIGS. 7 and 8 are views showing a third embodiment of the present invention. A third embodiment will be described based on FIGS. 7 and 8.

§1: Description of configuration of optical disk device ...
See FIG. 7. FIG. 7 is a block diagram of a disk control device according to the third embodiment.
Hereinafter, the configuration of the optical disc apparatus according to the third embodiment will be described with reference to FIG. In the third embodiment, the block diagram of the optical disk device shown in FIG. 2 is the same.

Further, the data buffer 8, multiplexer 9, comparator 10, RI pointer 11, RO pointer 1 provided in the disk controller of the first or second embodiment.
2, AND circuit 29, pointer control unit 30, register 3
Although 1 and the like are also provided in the third embodiment, they are omitted in the drawing.

As shown, the disk controller 5 has
A command control unit 6, a retry processing unit 7, a retry control unit 28, a retry timer unit 32, etc. are provided. The retry timer unit 32 measures and monitors the retry monitoring time at the time of retry. The rest of the configuration is the same as that of the first or second embodiment, and the description is omitted.

§2: Description of processing of the third embodiment--see FIG. 8 FIG. 8 is a time chart of the third embodiment. Hereinafter, the processing of the third embodiment will be described with reference to FIG.

The processing of the third embodiment is as follows. That is, as described in the first and second embodiments, the retry when an error occurs requires the host 1 to reissue the command, which increases the overhead of the host 1.

In order to reduce this, in the third embodiment, the retries within the connection monitoring time of the host 1 are processed in the disk control device 5, and only when the retries exceeding the above are necessary, Alternatively, the frequency of command reissue is reduced by performing the retry of the second embodiment.

As shown, the command RD from the host 1
It is assumed that -1 (first read command) is issued, and this command instructs the optical disk device to read the data blocks 1 to 3 on the medium.

At this time, under the control of the disk control device 5, the drive device 14 seeks to read the data blocks 1 to 3 on the medium. The data read from the medium is stored in the data buffer 8 and then sequentially read and transferred to the host 1 as described in the above embodiment. In this case, for example, it is assumed that an error (see the portion X in the figure) has occurred in the data block 3.

When an error occurs in this way, the control unit 1
The retry processing unit 7 which has received the error signal from 6 activates the retry timer unit 32 to start the measurement of the retry monitoring time.

Then, the drive unit 14 repeats the retry inside the device until the data block 3 is successfully retried. As a result, if the retry is successful and the data block 3 can be read, the data is transferred to the data buffer 8 and further transferred from the data buffer 8 to the host 1.

However, if the retry is not successful and the preset retry time T ₃ has elapsed, the retry timer section 32 times out and the retry control section 28 is activated. Then, as in the above-described embodiment, the retry control unit 28 reports the retry request “b” to the host 1.

According to this retry report, the read command is restarted (read command RD-2). In addition,
Subsequent processing is the same as that of the first or second embodiment, and the description thereof is omitted.

(Explanation of Fourth Embodiment) FIG. 9 is a view showing a fourth embodiment of the present invention. A fourth embodiment will be described with reference to FIG.

§1: Description of configuration of optical disk device ...
See FIG. 9. FIG. 9 is a block diagram of a disk controller according to the fourth embodiment.
Hereinafter, the configuration of the optical disc device according to the fourth embodiment will be described with reference to FIG. In addition, in the fourth embodiment, the retry determination unit 33 is further provided in the device of the third embodiment, and the other configuration is the same as that of the third embodiment (see FIG. 7).

As shown, the disk controller 5 has
A command control unit 6, a retry processing unit 7, a retry control unit 28, a retry timer unit 32, a retry determination unit 33, etc. are provided.

The retry judging section 33 judges the length of the processing time of the retry method "a" notified from the retry processing section 7 to the command control section 6, and switches the retry processing. The rest of the configuration is the same as that of the third embodiment, so the explanation is omitted.

§2: Description of Processing of Fourth Embodiment Hereinafter, processing of the fourth embodiment will be described. The process of Example 4 is as follows. That is, in the retry processing described in the third embodiment, since the system bus is occupied within the retry monitoring time, an I / O error does not occur, but the system bus overhead increases, which affects the system performance.

Therefore, in the fourth embodiment, the processing time of the retry method "a" is judged, and the processing is switched according to the judgment result (the processing of the first or second embodiment and the processing of the third embodiment. By switching), the retry time is shortened. This process is as follows.

For example, when an error occurs during the reading of the data block and the retry processing section 7 notifies the command control section 6 of the retry method "a", in the fourth embodiment, the retry determination section 33 causes the retry determination section 33 to perform the retry method. The processing time of "a" is determined.

Generally, the retry method of the optical disk device is roughly classified into "rotation waiting retry" and "GOHOME RETRY". "Retry waiting for rotation" requires several tens of ms, while "GO HOME RETRY" requires a retry time of 2 to 5 seconds.

Therefore, the retry determination unit 33 determines whether the retry method "a" from the retry processing unit 7 is "retry waiting for rotation" (retry for a short time) or "GO HOME RETRY".
"(Retry for a long time)" is determined, and retry switching is performed according to the determination result.

For example, when the retry method “a” is determined to be the short-time retry method, the retry determination unit 33
Notifies the command control unit 6 of the retry method "a" and activates the retry timer unit 32, thereby
Perform the same retry process as.

When it is determined that the retry method "a" is the long-time retry method, the retry determination unit 33
Retry request request signal “e” to the retry control unit 28
To notify and start. Upon receiving the retry request request signal “e”, the retry control unit 28 reports the retry request “b” to the host 1. After that, the same retry process as in the first or second embodiment is performed.

(Other Embodiments) Although the embodiments have been described above, the present invention can be implemented as follows. : The present invention is not limited to the optical disk device as in the above embodiment, but can be similarly applied to a magnetic disk device.

The optical disk device is not limited to the device of the above-described embodiment, but can be similarly applied to optical disk devices of other configurations.

[0115]

As described above, the present invention has the following effects. : When a read error occurs and retry processing is performed,
By performing the retry method as described in the above embodiment, the retry time can be shortened. As a result, the coupling time with the host can be shortened and the system bus can be prevented from being occupied for a long time.

Therefore, the system performance is improved. Also,
By occupying the system bus for a long time, the host can
It is also possible to prevent it from being determined as an / O error. In the retry method of the third embodiment, as described above, not only the retry time can be shortened, but also the host overhead due to command reissue can be reduced.

In the retry method of the fourth embodiment, as described above, not only the retry time can be shortened, but also the system bus overhead can be reduced.

[Brief description of drawings]

FIG. 1 is a diagram illustrating the principle of the present invention.

FIG. 2 is a block diagram of an optical disk device according to a first embodiment.

FIG. 3 is a block diagram of a disk control device according to the first embodiment.

FIG. 4 is a time chart of the first embodiment.

FIG. 5 is a block diagram of a disk controller according to a second embodiment.

FIG. 6 is a time chart of the second embodiment.

FIG. 7 is a block diagram of a disk controller according to a third embodiment.

FIG. 8 is a time chart of Example 3.

FIG. 9 is a block diagram of a disk control device according to a fourth embodiment.

FIG. 10 is an explanatory diagram 1 of the prior art.

FIG. 11 is an explanatory diagram 2 of the prior art.

[Explanation of symbols]

 5 disk control device 6 command control unit 7 retry processing unit 8 data buffer 9 multiplexer 10 comparator 11 RI pointer 12 RO pointer 14 drive device 28 retry control unit 29 AND circuit 30 pointer control unit 31 register 32 retry timer unit 33 retry determination unit

 ─────────────────────────────────────────────────── ─── Continuation of the front page (72) Inventor Takahiro Nakano No. 35 Saho, Shrine-cho, Kato-gun, Hyogo Prefecture (No address) Inside Fujitsu Peripherals Co., Ltd.

Claims (4)

[Claims] 1. A data buffer (8) for temporarily storing transfer data when transferring data read from a medium to a host (1), and a retry processing unit (7) for performing retry processing when a read error occurs. In a disk device that executes reading of multiple data blocks with one command, a retry control unit (28) that reports a retry request to the host (1) when a read error occurs, and a control of the retry control unit (28) Accordingly, a transfer mode switching means (29) for switching the transfer mode of the data buffer (8) is provided, and when a read error occurs, the retry control section (28).
A disk device characterized in that a retry request is reported to the host (1) by means of which the transfer mode switching means (29) switches the transfer mode so that re-command data transfer is performed in the buffer mode. 2. The disk device according to claim 1, further comprising pointer save means (30, 31) for saving a buffer pointer of a read data block, and the retry control unit (28) when a read error occurs.
Reports a retry request to the host (1) with
A disk device characterized in that the pointer save means (30, 31) saves a buffer pointer of a read data block and starts reading from an unread data block when a recommand is executed. 3. The disk device according to claim 1, further comprising a retry timer section (32) for monitoring a retry time, and the read timer section (3) when a read error occurs.
The retry time is monitored by 2), the retry is performed inside the device within the host monitoring time, and if it exceeds this, the retry control unit (28) is activated and a retry request is reported to the host (1). A disk device characterized by: 4. The disk device according to claim 3, further comprising a retry judging section (33) for judging whether the retry time is long or short and switching the retry, and when the read error occurs, the retry judging section (33).
The length of retry time is determined by the procedure. As a result, in the case of a retry that requires a long time, the retry control unit (28) is activated to report the retry request to the host, and in the case of a short retry, the above retry is performed. Timer part (3
The disk device characterized in that each of the retries switched according to the determination result of the retry determination unit is performed by activating 2) and monitoring the retry time.